feat: real-time reasoning speech, dynamic voice tags, and unified web UI bubbles

spoken_text.py

@@ -29,10 +29,12 @@ _LIST_MARKER = re.compile(r"^[ \t]*[-*•]\s+", re.MULTILINE)
 # Identifiers read better as words: "sample_rate" -> "sample rate".
 _UNDERSCORE_WORD = re.compile(r"(?<=\w)_(?=\w)")
 _EXTRA_SPACE = re.compile(r"[ \t]{2,}")
+_CONTROL_TAGS = re.compile(r"\[(COMPLETE|NEEDS_DEEP|STATUS:[^\]]+)\]", re.IGNORECASE)
+_VOICE_TAG = re.compile(r"\[Voice:\s*([a-zA-Z0-9_\-]+)\]", re.IGNORECASE)
 
 
 class SpokenTextFilter(MarkdownTextFilter):
-    """Markdown filtering, plus the leftovers that matter when read aloud."""
+    """Markdown filtering, plus voice tag parsing and leftovers that matter when read aloud."""
 
     def __init__(self, voice_manager=None, **kwargs):
         super().__init__(**kwargs)
@@ -41,8 +43,21 @@ class SpokenTextFilter(MarkdownTextFilter):
     async def filter(self, text: str) -> str:
         if self._voice_manager:
             self._voice_manager.sync_voice()
+
+        # Intercept and set active voice on [Voice:VoiceName] tags
+        match = _VOICE_TAG.search(text)
+        if match:
+            new_voice = match.group(1)
+            text = _VOICE_TAG.sub("", text)
+            if self._voice_manager:
+                try:
+                    self._voice_manager.set_voice(new_voice)
+                except Exception:
+                    pass
+
         text = _TIMES.sub(" times ", text)
         text = await super().filter(text)
+        text = _CONTROL_TAGS.sub("", text)
         text = _STRIKETHROUGH.sub(r"\1", text)
         text = _LIST_MARKER.sub("", text)
         text = _UNDERSCORE_WORD.sub(" ", text)